Naturalistic fMRI characterizes the brain as a dynamic predictive engine driven by continuous sensory streams. However, modeling the causal forward evolution in realistic neural simulation is impeded by the timescale mismatch between multimodal inputs and the complex topology of cortical networks. To address these challenges, we introduce BrainVista, a multimodal autoregressive framework designed to model the causal evolution of brain states. BrainVista incorporates Network-wise Tokenizers to disentangle system-specific dynamics and a Spatial Mixer Head that captures inter-network information flow without compromising functional boundaries. Furthermore, we propose a novel Stimulus-to-Brain (S2B) masking mechanism to synchronize high-frequency sensory stimuli with hemodynamically filtered signals, enabling strict, history-only causal conditioning. We validate our framework on Algonauts 2025, CineBrain, and HAD, achieving state-of-the-art fMRI encoding performance. In long-horizon rollout settings, our model yields substantial improvements over baselines, increasing pattern correlation by 36.0\% and 33.3\% on relative to the strongest baseline Algonauts 2025 and CineBrain, respectively.

翻译：自然主义功能磁共振成像将大脑表征为一个由连续感觉流驱动的动态预测引擎。然而，由于多模态输入与皮层网络复杂拓扑结构之间存在时间尺度不匹配，在真实神经模拟中对因果前向演化的建模受到阻碍。为应对这些挑战，我们提出了BrainVista，一个旨在建模大脑状态因果演化的多模态自回归框架。BrainVista集成了网络级标记器以解耦系统特异性动力学，以及一个空间混合头，用于在不损害功能边界的前提下捕获网络间的信息流。此外，我们提出了一种新颖的刺激到大脑掩蔽机制，以将高频感觉刺激与经过血流动力学滤波的信号同步，从而实现严格、仅基于历史的因果条件化。我们在Algonauts 2025、CineBrain和HAD数据集上验证了我们的框架，取得了最先进的功能磁共振成像编码性能。在长视野推演设置中，相较于最强基线，我们的模型在Algonauts 2025和CineBrain上分别将模式相关性提高了36.0%和33.3%。